A method to detect object grasping without tactile sensing on a humanoid robot

In future daily life, one of the most important functionality as a household service robot may be the delivery task. Furthermore, grasping an object is the essential motion for the delivery task. To complete the ordered delivery task successfully, robot should be able to detect whether its hand is grabbing the target object or not. If the object is released unexpectedly during service, robot has to recognize this abnormal situation properly. Most robots have used tactile sensors in their hands. In this paper, we present a novel method for detecting object grasping for complex hands of a humanoid robot without using tactile sensors. Joint torque values of fingers are exploited as information to predict the states of robotic hands.

[1]  Peter K. Allen,et al.  Blind grasping: Stable robotic grasping using tactile feedback and hand kinematics , 2011, 2011 IEEE International Conference on Robotics and Automation.

[2]  Peter K. Allen,et al.  An SVM learning approach to robotic grasping , 2004, IEEE International Conference on Robotics and Automation, 2004. Proceedings. ICRA '04. 2004.

[3]  DaeEun Kim,et al.  Visual navigation using pixel intensity information , 2012, 2012 12th International Conference on Control, Automation and Systems.

[4]  Siddhartha S. Srinivasa,et al.  Autonomous manipulation with a general-purpose simple hand , 2011, Int. J. Robotics Res..

[5]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[6]  L. Camarinha-Matos,et al.  A machine learning approach to error detection and recovery in assembly , 1995, Proceedings 1995 IEEE/RSJ International Conference on Intelligent Robots and Systems. Human Robot Interaction and Cooperative Robots.

[7]  Youngsu Park,et al.  An efficient localization method using RFID tag floor localization and dead reckoning , 2012, 2012 12th International Conference on Control, Automation and Systems.